Memory is critical for dialogue agents to maintain coherence and enable continuous adaptation in long-term interactions. While existing memory mechanisms offer basic storage and retrieval capabilities, they are hindered by two primary limitations: (1) rigid memory granularity often disrupts semantic integrity, resulting in fragmented and incoherent memory units; (2) prevalent flat retrieval paradigms rely solely on surface-level semantic similarity, neglecting the structural cues of discourse required to navigate and locate specific episodic contexts. To mitigate these limitations, drawing inspiration from Event Segmentation Theory, we propose ES-Mem, a framework incorporating two core components: (1) a dynamic event segmentation module that partitions long-term interactions into semantically coherent events with distinct boundaries; (2) a hierarchical memory architecture that constructs multi-layered memories and leverages boundary semantics to anchor specific episodic memory for precise context localization. Evaluations on two memory benchmarks demonstrate that ES-Mem yields consistent performance gains over baseline methods. Furthermore, the proposed event segmentation module exhibits robust applicability on dialogue segmentation datasets.
@article{arxiv.2601.07582,
title = {ES-Mem: Event Segmentation-Based Memory for Long-Term Dialogue Agents},
author = {Huhai Zou and Tianhao Sun and Chuanjiang He and Yu Tian and Zhenyang Li and Li Jin and Nayu Liu and Jiang Zhong and Kaiwen Wei},
journal= {arXiv preprint arXiv:2601.07582},
year = {2026}
}